AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Semantic Object Parsing with Graph LSTM

Xiaodan Liang, Xiaohui Shen, Jiashi Feng, Liang Lin, Shuicheng Yan

ECCV 2016 · Graph learning › Knowledge and temporal graphs · approach: Graph reasoning for visual recognition · 371 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use adaptive Graph LSTM instead of fixed factorized LG-LSTMsemantic parsing network · PASCAL-Person-Partaverage IoU (%): 57.97 -> 60.16Improved
use confidence-driven node updating instead of BFS (location) (ablation)Graph LSTM · PASCAL-Person-Partaverage IoU (%): 58.63 -> 60.16Improved
use confidence-driven node updating instead of DFS (confidence) (ablation)Graph LSTM · PASCAL-Person-Partaverage IoU (%): 59.21 -> 60.16Improved
add adaptive forget gates instead of identical forget gates (ablation)Graph LSTM · PASCAL-Person-Partaverage IoU (%): 59.21 -> 60.16Improved
add residual connections between Graph LSTM layers (ablation)Graph LSTM · PASCAL-Person-Partaverage IoU (%): 59.12 -> 60.16Improved
add Graph LSTM instead of superpixel smoothing post-processing on LG-LSTM (ablation)LG-LSTM · PASCAL-Person-Partaverage IoU (%): 58.58 -> 60.16Improved
add superpixel smoothing post-processing (ablation)LG-LSTM · PASCAL-Person-Partaverage IoU (%): 57.97 -> 58.58Improved
use confidences of head or torso label to order node updates instead of all foreground labels (ablation)Graph LSTM · PASCAL-Person-Partaverage IoU (%): 60.16 -> 61.03Mixed
increase superpixels beyond 1,000 per image (ablation)Graph LSTM · PASCAL-Person-Partaverage IoU (%)No clear effect
add 10,000 extra training imagesGraph LSTM · ATRaverage F-1 score (%): 83.76 -> 88.20Improved
add 10,000 extra training imagesGraph LSTM · Fashionistaaverage F-1 score (%): 87.57 -> 89.75Improved
use Graph LSTM instead of LG-LSTM (more)Graph LSTM (more) · ATRaverage F-1 score (%): 84.12 -> 88.20Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy